TRANSFER LEARNING PERFORMANCE FOR REMOTE PASTURELAND TRAIT ESTIMATION IN REAL-TIME FARM MONITORING

Patricia O'Byrne; Patrick Jackman; Damon Berry; Hector Hugo Franco-Peña; Michael French; Robert J. Ross

doi:10.1109/IGARSS47720.2021.9553222

TRANSFER LEARNING PERFORMANCE FOR REMOTE PASTURELAND TRAIT ESTIMATION IN REAL-TIME FARM MONITORING

Patricia O'Byrne, Patrick Jackman, Damon Berry, Hector Hugo Franco-Peña, Michael French, Robert J. Ross

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In precision agriculture, having knowledge of pastureland forage biomass and moisture content prior to an ensiling process enables pastoralists to enhance silage production.While traditional trait measurement estimation methods relied on hand-crafted vegetation indices, manual measurements, or even destructive methods, remote sensing technology coupled with state-of-the-art deep learning algorithms can enable estimation using a broader spectrum of data, but generally require large volumes of labelled data, which is lacking in this domain. This work investigates the performance of a range of deep learning algorithms on a small dataset for biomass and moisture estimation that was collected with a compact remote sensing system designed to work in real time. Our results showed that applying transfer learning to Inception ResNet improved minimum mean average percentage error from 45.58% on a basic CNN, to 28.07% on biomass, and from 29.33% to 8.03% on moisture content. From scratch models and models optimised for mobile remote sensing applications (MobileNet) failed to produce the same level of improvement.

Original language	English
Title of host publication	IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	4620-4623
Number of pages	4
ISBN (Electronic)	9781665403696
DOIs	https://doi.org/10.1109/IGARSS47720.2021.9553222
Publication status	Published - 2021
Event	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 - Brussels, Belgium Duration: 12 Jul 2021 → 16 Jul 2021

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2021-July

Conference

Conference	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Country/Territory	Belgium
City	Brussels
Period	12/07/21 → 16/07/21

Keywords

Grassland biomass
Inception ResNet
MobileNet
Proximal sensing
Transfer learning

Access to Document

10.1109/IGARSS47720.2021.9553222

https://arrow.tudublin.ie/scschcomcon/353Licence: CC BY-NC-SA

Cite this

O'Byrne, P., Jackman, P., Berry, D., Franco-Peña, H. H., French, M., & Ross, R. J. (2021). TRANSFER LEARNING PERFORMANCE FOR REMOTE PASTURELAND TRAIT ESTIMATION IN REAL-TIME FARM MONITORING. In IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 4620-4623). (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2021-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS47720.2021.9553222

O'Byrne, Patricia ; Jackman, Patrick ; Berry, Damon et al. / TRANSFER LEARNING PERFORMANCE FOR REMOTE PASTURELAND TRAIT ESTIMATION IN REAL-TIME FARM MONITORING. IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 4620-4623 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{a2166fde2dab4e3a8b8042d20f387380,

title = "TRANSFER LEARNING PERFORMANCE FOR REMOTE PASTURELAND TRAIT ESTIMATION IN REAL-TIME FARM MONITORING",

abstract = "In precision agriculture, having knowledge of pastureland forage biomass and moisture content prior to an ensiling process enables pastoralists to enhance silage production.While traditional trait measurement estimation methods relied on hand-crafted vegetation indices, manual measurements, or even destructive methods, remote sensing technology coupled with state-of-the-art deep learning algorithms can enable estimation using a broader spectrum of data, but generally require large volumes of labelled data, which is lacking in this domain. This work investigates the performance of a range of deep learning algorithms on a small dataset for biomass and moisture estimation that was collected with a compact remote sensing system designed to work in real time. Our results showed that applying transfer learning to Inception ResNet improved minimum mean average percentage error from 45.58% on a basic CNN, to 28.07% on biomass, and from 29.33% to 8.03% on moisture content. From scratch models and models optimised for mobile remote sensing applications (MobileNet) failed to produce the same level of improvement.",

keywords = "Grassland biomass, Inception ResNet, MobileNet, Proximal sensing, Transfer learning",

author = "Patricia O'Byrne and Patrick Jackman and Damon Berry and Franco-Pe{\~n}a, {Hector Hugo} and Michael French and Ross, {Robert J.}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 ; Conference date: 12-07-2021 Through 16-07-2021",

year = "2021",

doi = "10.1109/IGARSS47720.2021.9553222",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "4620--4623",

booktitle = "IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings",

address = "United States",

}

O'Byrne, P, Jackman, P, Berry, D, Franco-Peña, HH, French, M & Ross, RJ 2021, TRANSFER LEARNING PERFORMANCE FOR REMOTE PASTURELAND TRAIT ESTIMATION IN REAL-TIME FARM MONITORING. in IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2021-July, Institute of Electrical and Electronics Engineers Inc., pp. 4620-4623, 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021, Brussels, Belgium, 12/07/21. https://doi.org/10.1109/IGARSS47720.2021.9553222

TRANSFER LEARNING PERFORMANCE FOR REMOTE PASTURELAND TRAIT ESTIMATION IN REAL-TIME FARM MONITORING. / O'Byrne, Patricia; Jackman, Patrick; Berry, Damon et al.
IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. p. 4620-4623 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2021-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - TRANSFER LEARNING PERFORMANCE FOR REMOTE PASTURELAND TRAIT ESTIMATION IN REAL-TIME FARM MONITORING

AU - O'Byrne, Patricia

AU - Jackman, Patrick

AU - Berry, Damon

AU - Franco-Peña, Hector Hugo

AU - French, Michael

AU - Ross, Robert J.

PY - 2021

Y1 - 2021

N2 - In precision agriculture, having knowledge of pastureland forage biomass and moisture content prior to an ensiling process enables pastoralists to enhance silage production.While traditional trait measurement estimation methods relied on hand-crafted vegetation indices, manual measurements, or even destructive methods, remote sensing technology coupled with state-of-the-art deep learning algorithms can enable estimation using a broader spectrum of data, but generally require large volumes of labelled data, which is lacking in this domain. This work investigates the performance of a range of deep learning algorithms on a small dataset for biomass and moisture estimation that was collected with a compact remote sensing system designed to work in real time. Our results showed that applying transfer learning to Inception ResNet improved minimum mean average percentage error from 45.58% on a basic CNN, to 28.07% on biomass, and from 29.33% to 8.03% on moisture content. From scratch models and models optimised for mobile remote sensing applications (MobileNet) failed to produce the same level of improvement.

AB - In precision agriculture, having knowledge of pastureland forage biomass and moisture content prior to an ensiling process enables pastoralists to enhance silage production.While traditional trait measurement estimation methods relied on hand-crafted vegetation indices, manual measurements, or even destructive methods, remote sensing technology coupled with state-of-the-art deep learning algorithms can enable estimation using a broader spectrum of data, but generally require large volumes of labelled data, which is lacking in this domain. This work investigates the performance of a range of deep learning algorithms on a small dataset for biomass and moisture estimation that was collected with a compact remote sensing system designed to work in real time. Our results showed that applying transfer learning to Inception ResNet improved minimum mean average percentage error from 45.58% on a basic CNN, to 28.07% on biomass, and from 29.33% to 8.03% on moisture content. From scratch models and models optimised for mobile remote sensing applications (MobileNet) failed to produce the same level of improvement.

KW - Grassland biomass

KW - Inception ResNet

KW - MobileNet

KW - Proximal sensing

KW - Transfer learning

UR - http://www.scopus.com/inward/record.url?scp=85111862183&partnerID=8YFLogxK

U2 - 10.1109/IGARSS47720.2021.9553222

DO - 10.1109/IGARSS47720.2021.9553222

M3 - Conference contribution

AN - SCOPUS:85111862183

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 4620

EP - 4623

BT - IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021

Y2 - 12 July 2021 through 16 July 2021

ER -

O'Byrne P, Jackman P, Berry D, Franco-Peña HH, French M, Ross RJ. TRANSFER LEARNING PERFORMANCE FOR REMOTE PASTURELAND TRAIT ESTIMATION IN REAL-TIME FARM MONITORING. In IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2021. p. 4620-4623. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS47720.2021.9553222

TRANSFER LEARNING PERFORMANCE FOR REMOTE PASTURELAND TRAIT ESTIMATION IN REAL-TIME FARM MONITORING

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this